LLMHigh
CVE-2024-5565: The Vanna library uses a prompt function to present the user with visualized results, it is possible…
- Occurred
- May 31, 2024
- Published
- May 31, 2024
- Source
- NVD CVE
Summary
The Vanna library uses a prompt function to present the user with visualized results, it is possible to alter the prompt using prompt injection and run arbitrary Python code instead of the intended visualization code. Specifically - allowing external input to the library’s “ask” method with "visualize" set to True (default behavior) leads to remote code execution.
Tags
- CVE
- CVE-2024-5565
- cvss:HIGH
Classification
Category confidence: 90%
Severity confidence: 85%
Rationale: Prompt injection vulnerability in LLM library enables remote code execution, a critical security flaw.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8